tf.image.resize_with_pad

Resizes and pads an image to a target width and height.

tf.image.resize_with_pad(
    image,
    target_height,
    target_width,
    method=ResizeMethod.BILINEAR,
    antialias=False
)

Used in the notebooks

Used in the tutorials
Integrated gradients Load video data Transfer learning for video classification with MoViNet Video classification with a 3D convolutional neural network Image Classification with TensorFlow Hub

Resizes an image to a target width and height by keeping the aspect ratio the same without distortion. If the target dimensions don't match the image dimensions, the image is resized and then padded with zeroes to match requested dimensions.

Args
`image`	4-D Tensor of shape `[batch, height, width, channels]` or 3-D Tensor of shape `[height, width, channels]`.
`target_height`	Target height.
`target_width`	Target width.
`method`	Method to use for resizing image. See `image.resize()`
`antialias`	Whether to use anti-aliasing when resizing. See 'image.resize()'.

Raises
`ValueError`	if `target_height` or `target_width` are zero or negative.

Returns
Resized and padded image. If `images` was 4-D, a 4-D float Tensor of shape `[batch, new_height, new_width, channels]`. If `images` was 3-D, a 3-D float Tensor of shape `[new_height, new_width, channels]`.

© 2022 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 4.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/image/resize_with_pad